COVID19 UK

Prepare data

Read and format data

Prevalence

df_uk_prev <- read_csv('UK_timeseries_prep_2005.csv')

Parsed with column specification:
cols(
  ut_area = col_character(),
  date = col_character(),
  cumcase = col_double(),
  poptotal = col_double(),
  rate = col_double()
)

df_uk_prev <- df_uk_prev %>% 
  select(ut_area, date, rate) %>% 
  rename(rate_day = rate) %>%
  mutate(date = as.Date(date, "%d%b%Y"))

df_uk_prev

Personality

df_uk_pers <- read_csv('timeseries_uk_utla_march9_april_09.csv')

Parsed with column specification:
cols(
  ut_area = col_character(),
  time = col_double(),
  areaname = col_character(),
  open = col_double(),
  extra = col_double(),
  agree = col_double(),
  neuro = col_double(),
  sci = col_double(),
  frequ = col_double(),
  ut_name = col_character(),
  poptotal = col_double(),
  rate_day = col_double()
)

df_uk_pers <- df_uk_pers %>% 
  select(ut_area, open, agree, neuro, sci, extra) %>% 
  dplyr::rename(pers_o = open, 
         pers_c = sci,
         pers_e = extra,
         pers_a = agree,
         pers_n = neuro) %>%
  distinct()

df_uk_pers

NA

Social distancing

df_uk_socdist <- read_csv('UK_socdist_fb_nuts3.csv')

Parsed with column specification:
cols(
  nuts3 = col_character(),
  date = col_date(format = ""),
  all_day_bing_tiles_visited_relat = col_double(),
  all_day_ratio_single_tile_users = col_double(),
  open = col_double(),
  extra = col_double(),
  agree = col_double(),
  neuro = col_double(),
  sci = col_double(),
  frequ = col_double(),
  nuts3_name = col_character(),
  runday = col_double()
)

df_uk_socdist$date %>% summary()

        Min.      1st Qu.       Median         Mean      3rd Qu.         Max. 
"2020-03-01" "2020-03-08" "2020-03-16" "2020-03-16" "2020-03-24" "2020-03-31" 

df_uk_socdist <- df_uk_socdist %>% select(-runday, -frequ) %>%
  dplyr::rename(pers_o = open, 
                pers_c = sci,
                pers_e = extra,
                pers_a = agree,
                pers_n = neuro) %>% 
  select(-nuts3_name) %>% 
  dplyr::rename(socdist_tiles = all_day_bing_tiles_visited_relat,
                socdist_single_tile = all_day_ratio_single_tile_users) %>%
  drop_na()

df_uk_socdist

Controls

df_uk_ctrl_nuts <- read_csv("controls_UK_nuts3.csv")

Parsed with column specification:
cols(
  nuts3 = col_character(),
  nuts3_name = col_character(),
  airport_dist = col_double(),
  males = col_double(),
  popdens = col_double(),
  manufacturing = col_double(),
  tourism = col_double(),
  health = col_double(),
  academic = col_double(),
  medinc = col_double(),
  medage = col_double(),
  conservative = col_double()
)

df_uk_ctrl_nuts <- df_uk_ctrl_nuts %>% select(-nuts3_name)
df_uk_ctrl_nuts

df_uk_ctrl_ut <- read_csv("controls_UK_ut.csv")

Parsed with column specification:
cols(
  ut_area = col_character(),
  ut_name = col_character(),
  airport_dist = col_double(),
  males = col_double(),
  popdens = col_double(),
  manufacturing = col_double(),
  tourism = col_double(),
  health = col_double(),
  academic = col_double(),
  medinc = col_double(),
  medage = col_double(),
  conservative = col_double()
)

df_uk_ctrl_ut <- df_uk_ctrl_ut %>% select(-ut_name)
df_uk_ctrl_ut

NA
NA

Merge prevalence data

df_uk_prev <- df_uk_prev %>% 
  plyr::join(df_uk_pers, by='ut_area') %>% 
  plyr::join(df_uk_ctrl_ut, by='ut_area')

# create sequence of dates
date_sequence <- seq.Date(min(df_uk_prev$date),
                          max(df_uk_prev$date), 1)
                     
# create data frame with time sequence
df_dates = tibble(date_sequence, 1:length(date_sequence)) 
names(df_dates) <- c('date', 'time')

# merge day index with gps data
df_uk_prev = df_uk_prev %>% 
  merge(df_dates, by='date') %>% 
  arrange(ut_area) %>%
  as_tibble()

df_uk_prev

Merge social distancing data

nuts_ut_key <- read_csv('nuts3_ut.csv')

Parsed with column specification:
cols(
  nuts3 = col_character(),
  ut_area = col_character()
)

df_uk_socdist <- df_uk_socdist %>% plyr::join(df_uk_ctrl_nuts, by='nuts3')

df_uk_socdist <- nuts_ut_key %>% 
  inner_join(df_uk_socdist, by = c('nuts3')) %>%
  inner_join(select(df_uk_prev, ut_area, date, rate_day), by = c('ut_area', 'date')) %>%
  select(-ut_area)

# create sequence of dates
date_sequence <- seq.Date(min(df_uk_socdist$date),
                          max(df_uk_socdist$date), 1)
                     
# create data frame with time sequence
df_dates = tibble(date_sequence, 1:length(date_sequence)) 
names(df_dates) <- c('date', 'time')

# merge day index with gps data
df_uk_socdist = df_uk_socdist %>% 
  merge(df_dates, by='date') %>% 
  arrange(nuts3) %>%
  as_tibble()


df_uk_socdist

NA

Identify London areas

nuts_london_inner <- c('UKI31','UKI32','UKI33','UKI34','UKI41',
                      'UKI42','UKI43','UKI44','UKI45')

nuts_london_outer <- c('UKI51','UKI52','UKI53','UKI54','UKI61',
                      'UKI62','UKI63','UKI71','UKI72','UKI73',
                      'UKI74','UKI75')

ut_london_inner <- c('E09000007','E09000001','E09000033','E09000013',
                    'E09000020','E09000032','E09000025','E09000012',
                    'E09000030','E09000014','E09000019','E09000023',
                    'E09000028','E09000022')

ut_london_outer <- c('E09000011','E09000004','E09000016','E09000002',
                    'E09000031','E09000026','E09000010','E09000006',
                    'E09000008','E09000029','E09000021','E09000024',
                    'E09000003','E09000005','E09000009','E09000017',
                    'E09000015','E09000018','E09000027')

df_uk_prev = df_uk_prev %>% 
  mutate(london = ifelse(ut_area %in% ut_london_inner, 'london_inner', 
                       ifelse(ut_area %in% ut_london_outer, 'london_outer',
                              'country'))) %>%
  mutate(london = as.factor(london))

df_uk_socdist = df_uk_socdist %>% 
  mutate(london = ifelse(nuts3 %in% nuts_london_inner, 'london_inner', 
                       ifelse(nuts3 %in% nuts_london_outer, 'london_outer',
                              'country'))) %>%
  mutate(london = as.factor(london))

Check timeframes

df_uk_prev$date %>% summary()

        Min.      1st Qu.       Median         Mean      3rd Qu.         Max. 
"2020-01-30" "2020-02-26" "2020-03-24" "2020-03-24" "2020-04-21" "2020-05-18" 

df_uk_socdist$date %>% summary()

        Min.      1st Qu.       Median         Mean      3rd Qu.         Max. 
"2020-03-01" "2020-03-08" "2020-03-16" "2020-03-16" "2020-03-24" "2020-03-31" 

Control for weekend effect in social distancing

df_uk_loess <- df_uk_socdist %>% 
  mutate(weekday = format(date, '%u')) %>% 
  filter(!weekday %in% c('6','7')) %>% 
  split(.$nuts3) %>%
  map(~ loess(socdist_single_tile ~ time, data = .)) %>%
  map(predict, 1:max(df_uk_socdist$time)) %>% 
  bind_rows() %>% 
  gather(key = 'nuts3', value = 'loess') %>% 
  group_by(nuts3) %>% 
  mutate(time = row_number())

df_uk_loess

df_uk_socdist <- df_uk_socdist %>% merge(df_uk_loess, by=c('nuts3', 'time')) %>% 
  mutate(weekday = format(date, '%u')) %>% 
  mutate(socdist_single_tile_clean = ifelse(weekday %in% c('6','7'), loess,
                                            socdist_single_tile)) %>%
  arrange(nuts3, time) %>% 
  select(-weekday)


df_uk_socdist <- df_uk_socdist %>% drop_na() %>% mutate(time = time-1)

Explore data

Plot prevalence over time

df_uk_prev %>% ggplot(aes(x=time, y=rate_day)) + 
  geom_point(aes(col=ut_area, size=popdens)) + 
  geom_smooth(method="loess", se=T) + 
  theme(legend.position="none") +
  ggtitle("Overall prevalence over time")

pers <- c('pers_o', 'pers_c', 'pers_e', 'pers_a', 'pers_n')

for (i in pers){

gg <- df_uk_prev %>% mutate(prev_tail = cut(.[[i]], 
                                       breaks = c(-Inf, quantile(.[[i]], 0.2), quantile(.[[i]], 0.8), Inf),
                                       labels = c('lower tail', 'center', 'upper tail'))) %>% 
  filter(prev_tail != 'center') %>%
  ggplot(aes(x=time, y=rate_day)) + 
  geom_point(aes(col=ut_area, size=popdens)) + 
  geom_smooth(method="loess", se=T) + 
  facet_wrap(~prev_tail) + 
  theme(legend.position="none") +
  ggtitle(i)

print(gg)
}

Explore differences between london and the rest

df_uk_prev %>% ggplot(aes(x=time, y=rate_day)) + 
  geom_point(aes(col=ut_area, size=popdens)) + 
  geom_smooth(method="loess", se=T) + 
  theme(legend.position="none") +
  facet_wrap(~london) +
  ggtitle("Overall prevalence over time")

NA
NA
NA

Plot social distancing over time

df_uk_socdist %>% ggplot(aes(x=time, y=socdist_single_tile_clean)) + 
  geom_point(aes(col=nuts3, size=popdens)) + 
  geom_smooth(method="loess", se=T) + 
  theme(legend.position="none") +
  ggtitle("Overall social distancing over time")

pers <- c('pers_o', 'pers_c', 'pers_e', 'pers_a', 'pers_n')

for (i in pers){

gg <- df_uk_socdist %>% mutate(socdist_tail = cut(.[[i]], 
                                       breaks = c(-Inf, quantile(.[[i]], 0.2), quantile(.[[i]], 0.8), Inf),
                                       labels = c('lower tail', 'center', 'upper tail'))) %>% 
  filter(socdist_tail != 'center') %>%
  ggplot(aes(x=time, y=socdist_single_tile_clean)) + 
  geom_point(aes(col=nuts3, size=popdens)) + 
  geom_smooth(method="loess", se=T) + 
  facet_wrap(~socdist_tail) + 
  theme(legend.position="none") +
  ggtitle(i)

print(gg)
}

df_uk_socdist %>% ggplot(aes(x=time, y=socdist_single_tile_clean)) + 
  geom_point(aes(col=nuts3, size=popdens)) + 
  geom_smooth(method="loess", se=T) + 
  theme(legend.position="none") +
  facet_wrap(~london) +
  ggtitle("Overall social distancing over time")

df_uk_socdist <- df_uk_socdist %>% mutate(socdist_single_tile = socdist_single_tile_clean) %>% 
  select(-loess, -socdist_single_tile_clean)

Correlations

df_uk_prev %>% group_by(ut_area) %>% 
  summarize_if(is.numeric, mean, na.rm=T) %>% 
  select(-ut_area, -time) %>% 
  cor(use = 'pairwise.complete') %>% round(3) %>%
  as.data.frame()

df_uk_socdist %>% group_by(nuts3) %>% 
  summarize_if(is.numeric, mean, na.rm=T) %>% 
  select(-nuts3, -time) %>% 
  cor(use = 'pairwise.complete') %>% round(3) %>% 
  as.data.frame()

NA

Rescale Data

lvl2_scaled_ut <- df_uk_prev %>% 
  dplyr::select(-time, -date, -rate_day, -london) %>% 
  distinct() %>% 
  mutate_at(vars(-ut_area), scale)

lvl1_scaled_ut <- df_uk_prev %>% select(ut_area, time, rate_day)

df_uk_prev_scaled <- plyr::join(lvl1_scaled_ut, lvl2_scaled_ut, by = 'ut_area')

df_uk_prev_scaled

lvl2_scaled_nuts <- df_uk_socdist %>% 
  dplyr::select(-time, -date, -london, 
                -socdist_tiles, -socdist_single_tile, -rate_day) %>% 
  distinct() %>% 
  mutate_at(vars(-nuts3), scale)

lvl1_scaled_nuts <- df_uk_socdist %>% select(nuts3, time, socdist_single_tile, rate_day) %>% 
  mutate_at(vars(-nuts3, -time, - rate_day), scale)

df_uk_socdist_scaled <- plyr::join(lvl1_scaled_nuts, lvl2_scaled_nuts, by = 'nuts3')

df_uk_socdist_scaled

NA

Predict Prevalence

Extract first day of covid outbreak

# get onset day
df_uk_onset_prev <- df_uk_prev_scaled %>% 
  group_by(ut_area) %>% 
  mutate(rate_cs = cumsum(rate_day)) %>% 
  filter(rate_cs > 0) %>%
  summarize(onset_prev = min(time))
  
# merge with county data
df_uk_onset_prev <- df_uk_prev_scaled %>% 
  select(-time, -rate_day) %>%
  distinct() %>% 
  left_join(df_uk_onset_prev, by = 'ut_area')

# handle censored data
df_uk_onset_prev <- df_uk_onset_prev %>% 
  mutate(event = ifelse(is.na(onset_prev), 0, 1)) %>% 
  mutate(onset_prev = replace_na(onset_prev, as.numeric(diff(range(df_uk_prev$date)))+1))

Extract slopes

# cut time series before onset
df_uk_prev_scaled <- df_uk_prev_scaled %>% 
  group_by(ut_area) %>% 
  mutate(rate_cs = cumsum(rate_day)) %>% 
  filter(rate_cs > 0) %>%
  mutate(time = time-min(time)+1) %>%
  ungroup() %>%
  filter(time <= 30) %>%
  select(-rate_cs)

# drop counties with little data
df_uk_prev_scaled <- df_uk_prev_scaled %>%
  group_by(ut_area) %>%
  filter(n() == 30) %>%
  ungroup()

# extract slope prevalence
df_uk_slope_prev <- df_uk_prev_scaled %>% split(.$ut_area) %>% 
  map(~ lm(rate_day ~ time, data = .)) %>%
  map(coef) %>% 
  map_dbl('time') %>% 
  as.data.frame() %>% 
  rownames_to_column('ut_area') %>% 
  rename(slope_prev = '.')

# merge with county data
df_uk_slope_prev <- df_uk_prev_scaled %>% 
  select(-time, -rate_day) %>%
  distinct() %>% 
  inner_join(df_uk_slope_prev, by = 'ut_area') %>%
  drop_na()

# standardize slopes
df_uk_slope_prev <- df_uk_slope_prev %>% 
  mutate(slope_prev = scale(slope_prev))

Explore distributions

df_uk_onset_prev %>% ggplot(aes(onset_prev)) + geom_histogram()

df_uk_slope_prev %>% ggplot(aes(slope_prev)) + geom_histogram()

Predict COVID onset with time-to-event regression

# predict onset from personality
cox_onset_prev <- coxph(Surv(onset_prev, event) ~ 
                          pers_o + pers_c + pers_e + pers_a + pers_n, 
                        data = df_uk_onset_prev)
cox_onset_prev %>% summary()

Call:
coxph(formula = Surv(onset_prev, event) ~ pers_o + pers_c + pers_e + 
    pers_a + pers_n, data = df_uk_onset_prev)

  n= 149, number of events= 149 

            coef exp(coef)  se(coef)      z Pr(>|z|)  
pers_o  0.322264  1.380249  0.166864  1.931   0.0534 .
pers_c  0.036475  1.037149  0.135119  0.270   0.7872  
pers_e -0.013895  0.986201  0.143396 -0.097   0.9228  
pers_a  0.005323  1.005338  0.106927  0.050   0.9603  
pers_n -0.092400  0.911740  0.106197 -0.870   0.3843  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

       exp(coef) exp(-coef) lower .95 upper .95
pers_o    1.3802     0.7245    0.9952     1.914
pers_c    1.0371     0.9642    0.7958     1.352
pers_e    0.9862     1.0140    0.7446     1.306
pers_a    1.0053     0.9947    0.8153     1.240
pers_n    0.9117     1.0968    0.7404     1.123

Concordance= 0.605  (se = 0.027 )
Likelihood ratio test= 12.64  on 5 df,   p=0.03
Wald test            = 13.47  on 5 df,   p=0.02
Score (logrank) test = 13.78  on 5 df,   p=0.02

# predict onset from personality with controls
cox_onset_prev_ctrl <- coxph(Surv(onset_prev, event) ~ 
                               pers_o + pers_c + pers_e + pers_a + pers_n +
                               airport_dist + males + popdens + manufacturing + 
                               tourism + health + academic + medinc + medage +
                               conservative,
                             data = df_uk_onset_prev)
cox_onset_prev_ctrl %>% summary()

Call:
coxph(formula = Surv(onset_prev, event) ~ pers_o + pers_c + pers_e + 
    pers_a + pers_n + airport_dist + males + popdens + manufacturing + 
    tourism + health + academic + medinc + medage + conservative, 
    data = df_uk_onset_prev)

  n= 144, number of events= 144 
   (5 observations deleted due to missingness)

                  coef exp(coef) se(coef)      z Pr(>|z|)  
pers_o         0.13431   1.14375  0.26537  0.506   0.6128  
pers_c         0.27571   1.31746  0.21410  1.288   0.1978  
pers_e        -0.28546   0.75167  0.16166 -1.766   0.0774 .
pers_a         0.15618   1.16904  0.12936  1.207   0.2273  
pers_n        -0.04289   0.95801  0.13821 -0.310   0.7563  
airport_dist   0.08819   1.09219  0.10241  0.861   0.3892  
males         -0.28751   0.75013  0.11525 -2.495   0.0126 *
popdens        0.31764   1.37388  0.22294  1.425   0.1542  
manufacturing -0.01434   0.98576  0.15053 -0.095   0.9241  
tourism        0.20101   1.22263  0.12897  1.559   0.1191  
health        -0.13046   0.87769  0.09930 -1.314   0.1889  
academic       0.41323   1.51170  0.25879  1.597   0.1103  
medinc        -0.10312   0.90201  0.15281 -0.675   0.4998  
medage        -0.54104   0.58214  0.21413 -2.527   0.0115 *
conservative  -0.05175   0.94957  0.28447 -0.182   0.8557  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

              exp(coef) exp(-coef) lower .95 upper .95
pers_o           1.1438     0.8743    0.6799    1.9241
pers_c           1.3175     0.7590    0.8660    2.0044
pers_e           0.7517     1.3304    0.5475    1.0319
pers_a           1.1690     0.8554    0.9072    1.5064
pers_n           0.9580     1.0438    0.7307    1.2561
airport_dist     1.0922     0.9156    0.8936    1.3350
males            0.7501     1.3331    0.5985    0.9402
popdens          1.3739     0.7279    0.8875    2.1267
manufacturing    0.9858     1.0144    0.7339    1.3240
tourism          1.2226     0.8179    0.9496    1.5742
health           0.8777     1.1394    0.7225    1.0663
academic         1.5117     0.6615    0.9103    2.5104
medinc           0.9020     1.1086    0.6686    1.2170
medage           0.5821     1.7178    0.3826    0.8857
conservative     0.9496     1.0531    0.5437    1.6583

Concordance= 0.643  (se = 0.027 )
Likelihood ratio test= 37.26  on 15 df,   p=0.001
Wald test            = 39.13  on 15 df,   p=6e-04
Score (logrank) test = 40.98  on 15 df,   p=3e-04

Predict prevalence slopes with linear models

# predict slopes from personality
lm_slope_prev <- lm(slope_prev ~ pers_o + pers_c + pers_e + pers_a + pers_n, 
                         data = df_uk_slope_prev)
lm_slope_prev %>% summary()

Call:
lm(formula = slope_prev ~ pers_o + pers_c + pers_e + pers_a + 
    pers_n, data = df_uk_slope_prev)

Residuals:
    Min      1Q  Median      3Q     Max 
-1.7860 -0.6362 -0.2094  0.7033  2.6714 

Coefficients:
             Estimate Std. Error t value Pr(>|t|)   
(Intercept)  0.002131   0.079563   0.027  0.97867   
pers_o      -0.333971   0.156768  -2.130  0.03492 * 
pers_c      -0.410825   0.131422  -3.126  0.00216 **
pers_e       0.185648   0.146531   1.267  0.20731   
pers_a      -0.079900   0.113176  -0.706  0.48139   
pers_n      -0.010203   0.117778  -0.087  0.93109   
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.9544 on 138 degrees of freedom
Multiple R-squared:  0.121, Adjusted R-squared:  0.0892 
F-statistic: 3.801 on 5 and 138 DF,  p-value: 0.002952

lm_slope_prev %>% confint(level=0.9)

                    5 %        95 %
(Intercept) -0.12962227  0.13388435
pers_o      -0.59357311 -0.07436818
pers_c      -0.62845610 -0.19319326
pers_e      -0.05700314  0.42829908
pers_a      -0.26731588  0.10751684
pers_n      -0.20523983  0.18483327

# predict slopes from personality with controls
lm_slope_prev_ctrl <- lm(slope_prev ~  
                               pers_o + pers_c + pers_e + pers_a + pers_n +
                               airport_dist + males + popdens + manufacturing + 
                               tourism + health + academic + medinc + medage +
                               conservative,
                         data = df_uk_slope_prev)
lm_slope_prev_ctrl %>% summary()

Call:
lm(formula = slope_prev ~ pers_o + pers_c + pers_e + pers_a + 
    pers_n + airport_dist + males + popdens + manufacturing + 
    tourism + health + academic + medinc + medage + conservative, 
    data = df_uk_slope_prev)

Residuals:
    Min      1Q  Median      3Q     Max 
-1.5547 -0.6035 -0.1290  0.5089  2.5138 

Coefficients:
                Estimate Std. Error t value Pr(>|t|)  
(Intercept)    0.0001885  0.0762728   0.002   0.9980  
pers_o        -0.2077366  0.2283946  -0.910   0.3648  
pers_c        -0.4171252  0.1786161  -2.335   0.0211 *
pers_e         0.0766020  0.1510128   0.507   0.6128  
pers_a         0.0244037  0.1325550   0.184   0.8542  
pers_n        -0.0565544  0.1348334  -0.419   0.6756  
airport_dist  -0.2553608  0.1004444  -2.542   0.0122 *
males         -0.0929729  0.1132149  -0.821   0.4131  
popdens        0.3584047  0.1939178   1.848   0.0669 .
manufacturing  0.0044476  0.1308607   0.034   0.9729  
tourism       -0.0448877  0.1109015  -0.405   0.6863  
health         0.1020422  0.0961094   1.062   0.2904  
academic      -0.0444398  0.2325892  -0.191   0.8488  
medinc         0.2191543  0.1408175   1.556   0.1221  
medage         0.2639820  0.1864681   1.416   0.1593  
conservative   0.3114007  0.2528659   1.231   0.2204  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.9135 on 128 degrees of freedom
Multiple R-squared:  0.253, Adjusted R-squared:  0.1655 
F-statistic:  2.89 on 15 and 128 DF,  p-value: 0.0006055

lm_slope_prev_ctrl %>% confint(level=0.9)

                      5 %        95 %
(Intercept)   -0.12618377  0.12656074
pers_o        -0.58615113  0.17067793
pers_c        -0.71306452 -0.12118593
pers_e        -0.17360284  0.32680684
pers_a        -0.19521936  0.24402685
pers_n        -0.27995244  0.16684370
airport_dist  -0.42178168 -0.08893997
males         -0.28055246  0.09460666
popdens        0.03711285  0.67969647
manufacturing -0.21236829  0.22126358
tourism       -0.22863438  0.13885896
health        -0.05719619  0.26128051
academic      -0.42980408  0.34092454
medinc        -0.01415856  0.45246713
medage        -0.04496690  0.57293081
conservative  -0.10755887  0.73036030

CRF predicting slopes

ctrls <- cforest_unbiased(ntree=500, mtry=5)

crf_slope_prev <- cforest(slope_prev ~  
                               pers_o + pers_c + pers_e + pers_a + pers_n +
                               airport_dist + males + popdens + manufacturing + 
                               tourism + health + academic + medinc + medage +
                               conservative,
                           data = df_uk_slope_prev, 
                         controls = ctrls)

crf_slope_prev_varimp <- varimp(crf_slope_prev, nperm = 1)
crf_slope_prev_varimp_cond <- varimp(crf_slope_prev, conditional = T, nperm = 1)

crf_slope_prev_varimp

       pers_o        pers_c        pers_e        pers_a        pers_n  airport_dist 
 -0.001157014   0.053747726   0.001291754   0.020462011   0.005438448   0.108365253 
        males       popdens manufacturing       tourism        health      academic 
  0.007400495   0.092050722   0.003048002   0.010678059   0.004215513   0.016715474 
       medinc        medage  conservative 
  0.023809632   0.008239030   0.001390651 

crf_slope_prev_varimp %>% as.data.frame() %>% 
  rownames_to_column('variable') %>%
  ggplot(aes(x=variable, y=.)) +
  geom_bar(stat = 'identity') + 
  theme(axis.text.x = element_text(angle = 90))

crf_slope_prev_varimp_cond

       pers_o        pers_c        pers_e        pers_a        pers_n  airport_dist 
 0.0006295733  0.0561321826  0.0022530095  0.0196145597  0.0080475020  0.1003499343 
        males       popdens manufacturing       tourism        health      academic 
 0.0086626130  0.0903354666  0.0095705435  0.0125389217  0.0036556077  0.0123883068 
       medinc        medage  conservative 
 0.0237284345  0.0147654779  0.0047480179 

crf_slope_prev_varimp_cond %>% as.data.frame() %>% 
  rownames_to_column('variable') %>%
  ggplot(aes(x=variable, y=.)) +
  geom_bar(stat = 'identity') +
  theme(axis.text.x = element_text(angle = 90))

Predict Social Distancing

Change point analysis

# keep only counties with full data
nuts_complete <- df_uk_socdist_scaled %>% 
  group_by(nuts3) %>% 
  summarize(n = n()) %>% 
  filter(n==max(.$n)) %>% 
  .$nuts3

# run changepoint analysis
df_uk_socdist_cpt_results <- df_uk_socdist_scaled %>% 
  select(nuts3, socdist_single_tile) %>%
  filter(nuts3 %in% nuts_complete) %>% 
  split(.$nuts3) %>%
  map(~ cpt.meanvar(as.vector(.$socdist_single_tile),
                    #penalty = 'Asymptotic',
                    class=TRUE,
                    param.estimates=TRUE,
                    Q=1,
                    test.stat = 'Normal'))

# calculate change point
df_uk_socdist_cpt_day <- df_uk_socdist_cpt_results %>% 
  map(cpts) %>% 
  unlist() %>% 
  as.data.frame() %>% 
  rename(cpt_day_socdist = '.') %>%
  rownames_to_column('nuts3')

# calculate mean differences
df_uk_socdist_cpt_mean_diff <- df_uk_socdist_cpt_results %>% 
  map(param.est) %>% 
  map(~ .$mean) %>% 
  map(~ .[2]-.[1]) %>% 
  unlist() %>% 
  as.data.frame() %>% 
  rename(mean_diff_socdist = '.') %>%
  rownames_to_column('nuts3')

# calculate varaince differences
df_uk_socdist_cpt_var_diff <- df_uk_socdist_cpt_results %>% 
  map(param.est) %>% 
  map(~ .$variance) %>% 
  map(~ .[2]-.[1]) %>% 
  unlist() %>% 
  as.data.frame() %>% 
  rename(var_diff_socdist = '.') %>%
  rownames_to_column('nuts3')

# merge with county data
df_uk_cpt_socdist <- df_uk_socdist_scaled %>% 
  select(-time, -rate_day, -socdist_single_tile) %>%
  distinct() %>% 
  left_join(df_uk_socdist_cpt_day, by='nuts3') %>%
  left_join(df_uk_socdist_cpt_mean_diff, by='nuts3') %>%
  left_join(df_uk_socdist_cpt_var_diff, by='nuts3') %>%
  left_join(nuts_ut_key, by='nuts3') %>% 
  left_join(select(df_uk_onset_prev, ut_area, onset_prev), by='ut_area') %>%
  left_join(select(df_uk_slope_prev, ut_area, slope_prev), by='ut_area') %>%
  select(-ut_area)

# standardize mean/var differences
df_uk_cpt_socdist <- df_uk_cpt_socdist %>% 
  mutate(mean_diff_socdist = scale(mean_diff_socdist),
         var_diff_socdist = scale(var_diff_socdist))

# handle censored data
df_uk_cpt_socdist <- df_uk_cpt_socdist %>% 
  mutate(cpt_day_socdist = ifelse(is.na(cpt_day_socdist), 
                                  as.numeric(diff(range(df_us$date))), 
                                  cpt_day_socdist)) %>% 
  mutate(event = ifelse(cpt_day_socdist >= 60, 0, 1))

df_uk_cpt_socdist$cpt_day_socdist %>% hist()

df_uk_cpt_socdist$mean_diff_socdist %>% hist()

df_uk_cpt_socdist$var_diff_socdist %>% hist()

for(i in head(df_uk_socdist_cpt_results, 5)){
  plot(i)
}

NA

Predicting change points with time-to-event regression

# predict hazard from personality
cox_cpt_socdist <- coxph(Surv(cpt_day_socdist, event) ~ 
                           pers_o + pers_c + pers_e + pers_a + pers_n, 
                  data = df_uk_cpt_socdist)
cox_cpt_socdist %>% summary()

Call:
coxph(formula = Surv(cpt_day_socdist, event) ~ pers_o + pers_c + 
    pers_e + pers_a + pers_n, data = df_uk_cpt_socdist)

  n= 131, number of events= 131 

           coef exp(coef) se(coef)      z Pr(>|z|)
pers_o  0.02292   1.02319  0.14906  0.154    0.878
pers_c  0.01178   1.01185  0.14322  0.082    0.934
pers_e  0.17493   1.19117  0.14723  1.188    0.235
pers_a -0.19324   0.82428  0.11907 -1.623    0.105
pers_n -0.01502   0.98509  0.12389 -0.121    0.903

       exp(coef) exp(-coef) lower .95 upper .95
pers_o    1.0232     0.9773    0.7640     1.370
pers_c    1.0118     0.9883    0.7642     1.340
pers_e    1.1912     0.8395    0.8926     1.590
pers_a    0.8243     1.2132    0.6527     1.041
pers_n    0.9851     1.0151    0.7727     1.256

Concordance= 0.672  (se = 0.046 )
Likelihood ratio test= 11.4  on 5 df,   p=0.04
Wald test            = 13.38  on 5 df,   p=0.02
Score (logrank) test = 13.55  on 5 df,   p=0.02

# predict hazard from personality with controls
cox_cpt_socdist_ctrl <- coxph(Surv(cpt_day_socdist, event) ~ 
                                pers_o + pers_c + pers_e + pers_a + pers_n +
                               airport_dist + males + popdens + manufacturing + 
                               tourism + health + academic + medinc + medage +
                               conservative,
                  data = df_uk_cpt_socdist)
cox_cpt_socdist_ctrl %>% summary()

Call:
coxph(formula = Surv(cpt_day_socdist, event) ~ pers_o + pers_c + 
    pers_e + pers_a + pers_n + airport_dist + males + popdens + 
    manufacturing + tourism + health + academic + medinc + medage + 
    conservative, data = df_uk_cpt_socdist)

  n= 131, number of events= 131 

                   coef exp(coef)  se(coef)      z Pr(>|z|)  
pers_o        -0.100979  0.903952  0.243690 -0.414   0.6786  
pers_c        -0.048635  0.952528  0.198550 -0.245   0.8065  
pers_e         0.080996  1.084366  0.163732  0.495   0.6208  
pers_a        -0.006914  0.993110  0.162410 -0.043   0.9660  
pers_n         0.204498  1.226909  0.151016  1.354   0.1757  
airport_dist   0.251102  1.285441  0.126736  1.981   0.0476 *
males         -0.148267  0.862201  0.142494 -1.041   0.2981  
popdens        0.158406  1.171641  0.233680  0.678   0.4979  
manufacturing -0.083042  0.920313  0.130937 -0.634   0.5259  
tourism       -0.254837  0.775043  0.142800 -1.785   0.0743 .
health        -0.266804  0.765823  0.122195 -2.183   0.0290 *
academic       0.153738  1.166185  0.247465  0.621   0.5344  
medinc         0.166816  1.181537  0.177460  0.940   0.3472  
medage        -0.008602  0.991435  0.216020 -0.040   0.9682  
conservative  -0.180652  0.834726  0.268518 -0.673   0.5011  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

              exp(coef) exp(-coef) lower .95 upper .95
pers_o           0.9040     1.1063    0.5607    1.4574
pers_c           0.9525     1.0498    0.6455    1.4057
pers_e           1.0844     0.9222    0.7867    1.4947
pers_a           0.9931     1.0069    0.7224    1.3653
pers_n           1.2269     0.8151    0.9126    1.6495
airport_dist     1.2854     0.7779    1.0027    1.6479
males            0.8622     1.1598    0.6521    1.1400
popdens          1.1716     0.8535    0.7411    1.8523
manufacturing    0.9203     1.0866    0.7120    1.1896
tourism          0.7750     1.2903    0.5858    1.0254
health           0.7658     1.3058    0.6027    0.9731
academic         1.1662     0.8575    0.7180    1.8941
medinc           1.1815     0.8464    0.8344    1.6730
medage           0.9914     1.0086    0.6492    1.5141
conservative     0.8347     1.1980    0.4932    1.4129

Concordance= 0.756  (se = 0.043 )
Likelihood ratio test= 30.64  on 15 df,   p=0.01
Wald test            = 31.24  on 15 df,   p=0.008
Score (logrank) test = 32.93  on 15 df,   p=0.005

# predict hazard from personality with controls
cox_cpt_socdist_ctrl2 <- coxph(Surv(cpt_day_socdist, event) ~ 
                                 pers_o + pers_c + pers_e + pers_a + pers_n +
                               airport_dist + males + popdens + manufacturing + 
                               tourism + health + academic + medinc + medage +
                               conservative + onset_prev + slope_prev,
                  data = df_uk_cpt_socdist)
cox_cpt_socdist_ctrl2 %>% summary()

Call:
coxph(formula = Surv(cpt_day_socdist, event) ~ pers_o + pers_c + 
    pers_e + pers_a + pers_n + airport_dist + males + popdens + 
    manufacturing + tourism + health + academic + medinc + medage + 
    conservative + onset_prev + slope_prev, data = df_uk_cpt_socdist)

  n= 130, number of events= 130 
   (1 observation deleted due to missingness)

                   coef exp(coef)  se(coef)      z Pr(>|z|)  
pers_o        -0.100212  0.904646  0.249257 -0.402   0.6877  
pers_c        -0.116321  0.890189  0.207001 -0.562   0.5742  
pers_e         0.081829  1.085271  0.163065  0.502   0.6158  
pers_a         0.052790  1.054208  0.173127  0.305   0.7604  
pers_n         0.231265  1.260194  0.157150  1.472   0.1411  
airport_dist   0.216381  1.241576  0.129069  1.676   0.0936 .
males         -0.216077  0.805673  0.156020 -1.385   0.1661  
popdens        0.318647  1.375265  0.254074  1.254   0.2098  
manufacturing -0.068862  0.933456  0.131435 -0.524   0.6003  
tourism       -0.253111  0.776382  0.144734 -1.749   0.0803 .
health        -0.274628  0.759854  0.126715 -2.167   0.0302 *
academic       0.074328  1.077160  0.255443  0.291   0.7711  
medinc         0.275566  1.317276  0.187601  1.469   0.1419  
medage         0.044065  1.045050  0.217531  0.203   0.8395  
conservative  -0.168110  0.845261  0.269262 -0.624   0.5324  
onset_prev    -0.001956  0.998046  0.014702 -0.133   0.8941  
slope_prev    -0.190561  0.826495  0.166046 -1.148   0.2511  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

              exp(coef) exp(-coef) lower .95 upper .95
pers_o           0.9046     1.1054    0.5550    1.4745
pers_c           0.8902     1.1234    0.5933    1.3356
pers_e           1.0853     0.9214    0.7884    1.4940
pers_a           1.0542     0.9486    0.7509    1.4801
pers_n           1.2602     0.7935    0.9261    1.7148
airport_dist     1.2416     0.8054    0.9641    1.5990
males            0.8057     1.2412    0.5934    1.0939
popdens          1.3753     0.7271    0.8358    2.2628
manufacturing    0.9335     1.0713    0.7215    1.2077
tourism          0.7764     1.2880    0.5846    1.0310
health           0.7599     1.3160    0.5927    0.9741
academic         1.0772     0.9284    0.6529    1.7771
medinc           1.3173     0.7591    0.9120    1.9027
medage           1.0450     0.9569    0.6823    1.6007
conservative     0.8453     1.1831    0.4986    1.4328
onset_prev       0.9980     1.0020    0.9697    1.0272
slope_prev       0.8265     1.2099    0.5969    1.1444

Concordance= 0.745  (se = 0.044 )
Likelihood ratio test= 32.6  on 17 df,   p=0.01
Wald test            = 32.53  on 17 df,   p=0.01
Score (logrank) test = 33.98  on 17 df,   p=0.008

Linear models predicting mean differences

lm_meandiff_socdist <- lm(mean_diff_socdist ~ 
                            pers_o + pers_c + pers_e + pers_a + pers_n, 
                         data = df_uk_cpt_socdist)
lm_meandiff_socdist %>% summary()

Call:
lm(formula = mean_diff_socdist ~ pers_o + pers_c + pers_e + pers_a + 
    pers_n, data = df_uk_cpt_socdist)

Residuals:
     Min       1Q   Median       3Q      Max 
-1.64579 -0.51491 -0.01039  0.44273  2.01175 

Coefficients:
              Estimate Std. Error t value Pr(>|t|)    
(Intercept) -6.652e-16  6.716e-02   0.000 1.000000    
pers_o      -3.237e-02  1.226e-01  -0.264 0.792145    
pers_c      -2.732e-01  1.121e-01  -2.437 0.016220 *  
pers_e       4.179e-01  1.186e-01   3.523 0.000596 ***
pers_a      -1.442e-01  9.870e-02  -1.461 0.146648    
pers_n      -2.791e-02  9.783e-02  -0.285 0.775854    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.7687 on 125 degrees of freedom
Multiple R-squared:  0.4319,    Adjusted R-squared:  0.4092 
F-statistic: 19.01 on 5 and 125 DF,  p-value: 5.03e-14

lm_meandiff_socdist %>% confint(level=0.9)

                   5 %        95 %
(Intercept) -0.1112898  0.11128979
pers_o      -0.2354792  0.17074155
pers_c      -0.4590535 -0.08743620
pers_e       0.2213206  0.61442966
pers_a      -0.3077064  0.01940226
pers_n      -0.1900323  0.13420232

lm_meandiff_socdist_ctrl <- lm(mean_diff_socdist ~ 
                                 pers_o + pers_c + pers_e + pers_a + pers_n +
                               airport_dist + males + popdens + manufacturing + 
                               tourism + health + academic + medinc + medage +
                               conservative,
                            data = df_uk_cpt_socdist)
lm_meandiff_socdist_ctrl %>% summary()

Call:
lm(formula = mean_diff_socdist ~ pers_o + pers_c + pers_e + pers_a + 
    pers_n + airport_dist + males + popdens + manufacturing + 
    tourism + health + academic + medinc + medage + conservative, 
    data = df_uk_cpt_socdist)

Residuals:
     Min       1Q   Median       3Q      Max 
-1.67572 -0.44003 -0.00968  0.35644  1.43938 

Coefficients:
                Estimate Std. Error t value Pr(>|t|)    
(Intercept)    1.736e-15  5.265e-02   0.000   1.0000    
pers_o        -2.278e-01  1.536e-01  -1.483   0.1407    
pers_c        -9.103e-02  1.238e-01  -0.735   0.4638    
pers_e         8.363e-02  1.022e-01   0.819   0.4148    
pers_a         2.510e-01  9.761e-02   2.571   0.0114 *  
pers_n         1.598e-01  8.524e-02   1.875   0.0633 .  
airport_dist  -1.452e-01  7.427e-02  -1.955   0.0530 .  
males         -1.790e-01  8.763e-02  -2.043   0.0434 *  
popdens        6.472e-01  1.373e-01   4.713  6.9e-06 ***
manufacturing -1.761e-01  8.167e-02  -2.156   0.0332 *  
tourism       -7.244e-02  7.820e-02  -0.926   0.3562    
health        -3.648e-03  6.918e-02  -0.053   0.9580    
academic       1.971e-01  1.538e-01   1.282   0.2025    
medinc         1.833e-01  1.014e-01   1.809   0.0731 .  
medage        -9.010e-03  1.351e-01  -0.067   0.9469    
conservative  -3.433e-02  1.725e-01  -0.199   0.8427    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.6026 on 115 degrees of freedom
Multiple R-squared:  0.6787,    Adjusted R-squared:  0.6368 
F-statistic:  16.2 on 15 and 115 DF,  p-value: < 2.2e-16

lm_meandiff_socdist_ctrl %>% confint(level=0.9)

                      5 %        95 %
(Intercept)   -0.08730925  0.08730925
pers_o        -0.48240052  0.02684553
pers_c        -0.29639278  0.11433553
pers_e        -0.08579590  0.25305877
pers_a         0.08909523  0.41281599
pers_n         0.01848059  0.30116470
airport_dist  -0.26833237 -0.02203087
males         -0.32433391 -0.03370903
popdens        0.41946976  0.87487594
manufacturing -0.31150145 -0.04065515
tourism       -0.20212145  0.05723813
health        -0.11836208  0.11106574
academic      -0.05790764  0.45210902
medinc         0.01525667  0.35142884
medage        -0.23303105  0.21501107
conservative  -0.32043114  0.25177936

lm_meandiff_socdist_ctrl2 <- lm(mean_diff_socdist ~ 
                                  pers_o + pers_c + pers_e + pers_a + pers_n +
                               airport_dist + males + popdens + manufacturing + 
                               tourism + health + academic + medinc + medage +
                               conservative + onset_prev + slope_prev,
                            data = df_uk_cpt_socdist)
lm_meandiff_socdist_ctrl2 %>% summary()

Call:
lm(formula = mean_diff_socdist ~ pers_o + pers_c + pers_e + pers_a + 
    pers_n + airport_dist + males + popdens + manufacturing + 
    tourism + health + academic + medinc + medage + conservative + 
    onset_prev + slope_prev, data = df_uk_cpt_socdist)

Residuals:
     Min       1Q   Median       3Q      Max 
-1.73062 -0.41506  0.00236  0.39176  1.51083 

Coefficients:
               Estimate Std. Error t value Pr(>|t|)    
(Intercept)    0.298362   0.279045   1.069   0.2873    
pers_o        -0.246641   0.155683  -1.584   0.1160    
pers_c        -0.063355   0.124995  -0.507   0.6133    
pers_e         0.087719   0.102359   0.857   0.3933    
pers_a         0.248985   0.097577   2.552   0.0121 *  
pers_n         0.152392   0.085413   1.784   0.0771 .  
airport_dist  -0.124048   0.075185  -1.650   0.1018    
males         -0.125131   0.093003  -1.345   0.1812    
popdens        0.599144   0.143775   4.167 6.09e-05 ***
manufacturing -0.182290   0.082628  -2.206   0.0294 *  
tourism       -0.077232   0.078515  -0.984   0.3274    
health        -0.006028   0.069266  -0.087   0.9308    
academic       0.197328   0.154892   1.274   0.2053    
medinc         0.149825   0.103537   1.447   0.1507    
medage        -0.003030   0.135821  -0.022   0.9822    
conservative  -0.054715   0.172815  -0.317   0.7521    
onset_prev    -0.008423   0.008221  -1.025   0.3078    
slope_prev     0.158185   0.088247   1.793   0.0757 .  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.602 on 112 degrees of freedom
  (1 observation deleted due to missingness)
Multiple R-squared:  0.6857,    Adjusted R-squared:  0.638 
F-statistic: 14.38 on 17 and 112 DF,  p-value: < 2.2e-16

lm_meandiff_socdist_ctrl2 %>% confint(level=0.9)

                      5 %          95 %
(Intercept)   -0.16445432  0.7611787168
pers_o        -0.50485339  0.0115709223
pers_c        -0.27066775  0.1439583777
pers_e        -0.08205015  0.2574879916
pers_a         0.08714679  0.4108234557
pers_n         0.01072830  0.2940549875
airport_dist  -0.24874786  0.0006528252
males         -0.27938403  0.0291211026
popdens        0.36068190  0.8376060752
manufacturing -0.31933404 -0.0452456984
tourism       -0.20745495  0.0529914399
health        -0.12090990  0.1088538858
academic      -0.05957178  0.4542275782
medinc        -0.02189838  0.3215476531
medage        -0.22829969  0.2222397258
conservative  -0.34134071  0.2319101786
onset_prev    -0.02205782  0.0052120593
slope_prev     0.01182114  0.3045482089

CRF predicting mean difference

ctrls <- cforest_unbiased(ntree=500, mtry=5)

crf_meandiff_socdist <- cforest(mean_diff_socdist ~ 
                                  pers_o + pers_c + pers_e + pers_a + pers_n +
                               airport_dist + males + popdens + manufacturing + 
                               tourism + health + academic + medinc + medage +
                               conservative + onset_prev + slope_prev,
                               data = df_uk_cpt_socdist %>% drop_na(),
                         controls = ctrls)

crf_meandiff_socdist_varimp <- varimp(crf_meandiff_socdist, nperm = 1)
crf_meandiff_socdist_varimp_cond <- varimp(crf_meandiff_socdist, conditional = T, nperm = 1)

crf_meandiff_socdist_varimp

       pers_o        pers_c        pers_e        pers_a        pers_n  airport_dist 
 0.0232844793  0.0122480819  0.0403477261  0.0059899957 -0.0005080761  0.0450846205 
        males       popdens manufacturing       tourism        health      academic 
 0.0008135687  0.2838876443  0.0443088789  0.0069334919  0.0020621555  0.1013815679 
       medinc        medage  conservative    onset_prev    slope_prev 
 0.0923793299  0.0412885652  0.1093241022  0.0007741436  0.0078232998 

crf_meandiff_socdist_varimp %>% as.data.frame() %>% 
  rownames_to_column('variable') %>%
  ggplot(aes(x=variable, y=.)) +
  geom_bar(stat = 'identity') +
  theme(axis.text.x = element_text(angle = 90))

crf_meandiff_socdist_varimp_cond

       pers_o        pers_c        pers_e        pers_a        pers_n  airport_dist 
 2.220321e-02  1.266544e-02  3.619921e-02  2.757494e-03 -1.068532e-04  5.066091e-02 
        males       popdens manufacturing       tourism        health      academic 
 5.051975e-04  2.708944e-01  3.938252e-02  6.477050e-03  2.565017e-03  9.055470e-02 
       medinc        medage  conservative    onset_prev    slope_prev 
 9.946050e-02  4.130137e-02  1.009788e-01 -3.928147e-05  1.067222e-02 

crf_meandiff_socdist_varimp_cond %>% as.data.frame() %>% 
  rownames_to_column('variable') %>%
  ggplot(aes(x=variable, y=.)) +
  geom_bar(stat = 'identity') +
  theme(axis.text.x = element_text(angle = 90))

Export data

uk_list_results <- list(cox_onset_prev, cox_onset_prev_ctrl, 
     lm_slope_prev, lm_slope_prev_ctrl, 
     cox_cpt_socdist, cox_cpt_socdist_ctrl, cox_cpt_socdist_ctrl2,
     lm_meandiff_socdist, lm_meandiff_socdist_ctrl, lm_meandiff_socdist_ctrl2)

results_names <- list('cox_onset_prev', 'cox_onset_prev_ctrl', 
     'lm_slope_prev', 'lm_slope_prev_coef', 
     'cox_cpt_socdist', 'cox_cpt_socdist_ctrl', 'cox_cpt_socdist_ctrl2',
     'lm_meandiff_socdist', 'lm_meandiff_socdist_ctrl', 'lm_meandiff_socdist_ctrl2')

names(uk_list_results) <- results_names

save(uk_list_results, file="uk_list_results.RData")

write_csv(df_uk_slope_prev, 'df_uk_slope_prev.csv')
write_csv(df_uk_cpt_socdist, 'df_uk_cpt_socdist.csv')